arXiv subjects

Kexue Fu

Publications and source records attributed to Kexue Fu.

At least 19 recordsLinked to original sources

arXiv2026

Close Shortcut Wins Long: Seeking Diverse and Stable Generators for Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) preserves privacy by transferring knowledge without real data access. However, existing generator-based DFKD methods suffer from over-reliance on teacher preferences and pattern collapse, exhibiting "generative shortcut learning" in the frequency domain: dependent on specific frequency components and frequency positions, resulting in inconsistent synthetic image quality and class diversity. In this paper, we propose a CSWL framework aimed at introducing insights from the frequency domain perspective to improve generator diversity and training stability to Close the phenomenon of Shortcut learning to Win in the Longer term. To address the issue of generative shortcut learning, we introduce frequency-domain augmentation at the feature level, encouraging the generator to attend to the full frequency spectrum and thereby suppress shortcut learning behavior. To tackle training instability, we propose a Cross-Stage Frequency Reconstruction (CSFR) auxiliary task, which implicitly constructs an Exponential Moving Average (EMA) mechanism to promote long-term optimization and stability. Extensive experiments, including downstream tasks and various image recognition datasets at multiple resolutions, validate the effectiveness of CSWL in improving both diversity and stability from the frequency view.

cs.CV↗

arXiv2026

DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to generate CAMs in WSSS. However, previous WSSS methods solely adopt CLIP's vision-language paired property for dense localization, neglecting its inherently limited dense knowledge across both visual and text modalities, which renders CAM generation suboptimal. In this work, we propose DiCLIP, a novel WSSS framework that leverages the generative diffusion model to enhance CLIP's dense knowledge across two modalities. Specifically, Visual Correlation Enhancement (VCE) and Text Semantic Augmentation (TSA) modules are proposed for dense prediction enhancement. To improve the spatial awareness of visual features, our VCE module utilizes diffusion's reliable spatial consistency to mitigate the over-smoothing issue in CLIP's attention. It designs the Attention Clustering Refinement (ACR) module to reliably extract diverse correlation maps from the diffusion model. The correlation maps act as a diversity bias for CLIP's self-attention, recursively pushing its visual features towards a more discriminative dense distribution. To augment the semantics of text embeddings, our TSA module argues that a single text modality is insufficient to encompass the variability of visual categories. Thus, we leverage diffusion's generative power to maintain a dynamic key-value cache model, shifting CAM generation from a patch-text matching mechanism to a novel visual knowledge retrieval paradigm. With these enhancements, DiCLIP not only outperforms state-of-the-art methods on PASCAL VOC and MS COCO but also significantly reduces training costs. Code is publicly available at https://github.com/zwyang6/DiCLIP.

cs.CV↗

arXiv2026

Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition

Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasing caused by irrelevant regions and inefficient re-ranking due to rigid candidate scheduling. To address these issues, we introduce FoL++, a method combining robust discriminative region modeling with adaptive re-ranking. Specifically, we propose a Reliability Estimation Branch to generate spatial reliability maps that explicitly model occlusion resistance. This representation is further optimized by two spatial alignment losses (SAL and SCEL) to effectively align features and highlight salient regions. For weakly supervised learning without manual annotations, a pseudo-correspondence strategy generates dense local feature supervision directly from aggregation clusters. Our Adaptive Candidate Scheduler dynamically resizes candidate pools based on global similarity. By weighting local matches by reliability and adaptively fusing global and local evidence, FoL++ surpasses traditional independent matching systems. Extensive experiments across seven benchmarks demonstrate that FoL++ achieves state-of-the-art performance with a lightweight memory footprint, improving inference speed by 40% over FoL. Code and models will be released (and merged with FoL) at https://github.com/chenshunpeng/FoL.

cs.CV↗

arXiv2026

The Configuration of Space: Probing the Way Social Interaction and Perception are Affected by Task-Specific Spatial Representations in Online Video Communication

Humans live and act in 3D space, but often work and communicate on 2D surfaces. The prevalence of online communication on 2D screens raises the issue of whether human spatial configuration affects our capabilities, social perception, and behaviors when interacting with others in 2D video chat. How do factors like location, setting, and context subtly shape our online communication, particularly in scenarios such as social support and topic-based discussions? Using Ohyay.co as a platform, we compared a normal gallery interface with a scene-based Room-type interface where participants are located in circular arrangement on screen in a social support task, and found that participants allocated attention to the group as a whole, and had pronounced self-awareness in the Room format. We then chose a two-sided topic for discussion in the Gallery interface and the Room interface where participants on each team face-off against each other, and found that they utilized spatial references to orient their allegiances, expressing greater engagement with those farther away in digital space and greater empathy with those closer, in the Room over the Gallery format. We found spatial effects in the way participants hide from the spotlight, in perspective-taking, and in their use of expressive gestures in time on the screen. This work highlights the need for considering spatial configuration in 2D in the design of collaborative communication systems to optimize for psychological needs for particular tasks.

cs.HC↗

arXiv2026

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis

Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive schedules, and limited acceleration scope, thereby leaving significant acceleration potential untapped. Since entropy variation intrinsically reflects the transition of predictive uncertainty, it offers a principled measure to capture modeling dynamics evolution. Therefore, we propose NOVA, a training-free token reduction acceleration framework for VAR models via entropy analysis. NOVA adaptively determines the acceleration activation scale during inference by online identifying the inflection point of scale entropy growth. Through scale-linkage and layer-linkage ratio adjustment, NOVA dynamically computes distinct token reduction ratios for each scale and layer, pruning low-entropy tokens while reusing the cache derived from the residuals at the prior scale to accelerate inference and maintain generation quality. Extensive experiments and analyses validate NOVA as a simple yet effective training-free acceleration framework.

cs.CV↗

arXiv2026

Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model

Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention. The emergence of CLIP has spurred extensive research into zero-shot OOD detection, often employing a training-free approach. Current methods leverage expert knowledge from large language models (LLMs) to identify potential outliers. However, these approaches tend to over-rely on knowledge in the text space, neglecting the inherent challenges involved in detecting out-of-distribution samples in the image space. In this paper, we propose a novel pipeline, MM-OOD, which leverages the multimodal reasoning capabilities of MLLMs and their ability to conduct multi-round conversations for enhanced outlier detection. Our method is designed to improve performance in both near OOD and far OOD tasks. Specifically, (1) for near OOD tasks, we directly feed ID images and corresponding text prompts into MLLMs to identify potential outliers; and (2) for far OOD tasks, we introduce the sketch-generate-elaborate framework: first, we sketch outlier exposure using text prompts, then generate corresponding visual OOD samples, and finally elaborate by using multimodal prompts. Experiments demonstrate that our method achieves significant improvements on widely used multimodal datasets such as Food-101, while also validating its scalability on ImageNet-1K.

cs.CV↗

arXiv2025

CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion

Semantic Scene Completion (SSC) aims to infer complete 3D geometry and semantics from monocular images, serving as a crucial capability for camera-based perception in autonomous driving. However, existing SSC methods relying on temporal stacking or depth projection often lack explicit motion reasoning and struggle with occlusions and noisy depth supervision. We propose CurriFlow, a novel semantic occupancy prediction framework that integrates optical flow-based temporal alignment with curriculum-guided depth fusion. CurriFlow employs a multi-level fusion strategy to align segmentation, visual, and depth features across frames using pre-trained optical flow, thereby improving temporal consistency and dynamic object understanding. To enhance geometric robustness, a curriculum learning mechanism progressively transitions from sparse yet accurate LiDAR depth to dense but noisy stereo depth during training, ensuring stable optimization and seamless adaptation to real-world deployment. Furthermore, semantic priors from the Segment Anything Model (SAM) provide category-agnostic supervision, strengthening voxel-level semantic learning and spatial consistency. Experiments on the SemanticKITTI benchmark demonstrate that CurriFlow achieves state-of-the-art performance with a mean IoU of 16.9, validating the effectiveness of our motion-guided and curriculum-aware design for camera-based 3D semantic scene completion.

cs.CV↗

arXiv2025

Vistoria: A Multimodal System to Support Fictional Story Writing through Instrumental Text-Image Co-Editing

Humans think visually-we remember in images, dream in pictures, and use visual metaphors to communicate. Yet, most creative writing tools remain text-centric, limiting how authors plan and translate ideas. We present Vistoria, a system for synchronized text-image co-editing in fictional story writing that treats visuals and text as coequal narrative materials. A formative Wizard-of-Oz co-design study with 10 story writers revealed how sketches, images, and annotations serve as essential instruments for ideation and organization. Drawing on theories of Instrumental Interaction and Structural Mapping, Vistoria introduces multimodal operations-lasso, collage, filters, and perspective shifts that enable seamless narrative exploration across modalities. A controlled study with 12 participants shows that co-editing enhances expressiveness, immersion, and collaboration, enabling writers to explore divergent directions, embrace serendipitous randomness, and trace evolving storylines. While multimodality increased cognitive demand, participants reported stronger senses of authorship and agency. These findings demonstrate how multimodal co-editing expands creative potential by balancing abstraction and concreteness in narrative development.

cs.HC↗

arXiv2025

Spatial Balancing: Designing an LLM-Powered Spatial Externalization Interface for Iterative Science Communication Writing

Science communication revision requires writers to dynamically balance scientific exposition and narrative engagement - a process where writers often struggle with competing directions. Existing LLM-assisted tools help with co-writing, but offer limited support for navigating this iterative, multi-directional revision process. To address this gap, we designed Spatial Balancing, an exploratory revision environment that maps rhetorical goals and revision strategies onto a two-dimensional spatial canvas for experienced science communication creators with domain expertise but lacking formal professional training. By building a design space of communication strategies and embedding them into a spatial exploratory canvas, our system treats feedback as navigational cues rather than prescriptive judgments. Our findings show that this integrated revision environment helps writers stay focused on writing goals, reason about revision as trajectories, and explore alternatives, which supports greater metacognitive control and confidence without increasing workload. This work highlights the value of spatially externalized revision environments for supporting iterative, reflective thinking during LLM-assisted writing.

cs.HC↗

arXiv2025

A Constructed Response: Designing and Choreographing Robot Arm Movements in Collaborative Dance Improvisation

Dancers often prototype movements themselves or with each other during improvisation and choreography. How are these interactions altered when physically manipulable technologies are introduced into the creative process? To understand how dancers design and improvise movements while working with instruments capable of non-humanoid movements, we engaged dancers in workshops to co-create movements with a robot arm in one-human-to-one-robot and three-human-to-one-robot settings. We found that dancers produced more fluid movements in one-to-one scenarios, experiencing a stronger sense of connection and presence with the robot as a co-dancer. In three-to-one scenarios, the dancers divided their attention between the human dancers and the robot, resulting in increased perceived use of space and more stop-and-go movements, perceiving the robot as part of the stage background. This work highlights how technologies can drive creativity in movement artists adapting to new ways of working with physical instruments, contributing design insights supporting artistic collaborations with non-humanoid agents.

cs.RO↗

arXiv2025

From Temporal to Spatial: Designing Spatialized Interactions with Segmented-audios in Immersive Environments for Active Engagement with Performing Arts Intangible Cultural Heritage

Performance artforms like Peking opera face transmission challenges due to the extensive passive listening required to understand their nuance. To create engaging forms of experiencing auditory Intangible Cultural Heritage (ICH), we designed a spatial interaction-based segmented-audio (SISA) Virtual Reality system that transforms passive ICH experiences into active ones. We undertook: (1) a co-design workshop with seven stakeholders to establish design requirements, (2) prototyping with five participants to validate design elements, and (3) user testing with 16 participants exploring Peking Opera. We designed transformations of temporal music into spatial interactions by cutting sounds into short audio segments, applying t-SNE algorithm to cluster audio segments spatially. Users navigate through these sounds by their similarity in audio property. Analysis revealed two distinct interaction patterns (Progressive and Adaptive), and demonstrated SISA's efficacy in facilitating active auditory ICH engagement. Our work illuminates the design process for enriching traditional performance artform using spatially-tuned forms of listening.

cs.HC↗

arXiv2025

RetroChat: Designing for the Preservation of Past Digital Experiences

Rapid changes in social networks have transformed the way people express themselves, turning past neologisms, values, and mindsets embedded in these expressions into online heritage. How can we preserve these expressions as cultural heritage? Instead of traditional archiving methods for static material, we designed an interactive and experiential form of archiving for Chinese social networks. Using dialogue data from 2000-2010 on early Chinese social media, we developed a GPT-driven agent within a retro chat interface, emulating the language and expression style of the period for interaction. Results from a qualitative study with 18 participants show that the design captures the past chatting experience and evokes memory flashbacks and nostalgia feeling through conversation. Participants, particularly those familiar with the era, adapted their language to match the agent's chatting style. This study explores how the design of preservation methods for digital experiences can be informed by experiential representations supported by generative tools.

cs.HC↗

arXiv2025

Large Language Model-Based Intelligent Antenna Design System

Antenna simulation typically involves modeling and optimization, which are time-consuming and labor-intensive, slowing down antenna analysis and design. This paper presents a prototype of a large language model (LLM)-based antenna design system (LADS) to assist in antenna simulation. LADS generates antenna models with textual descriptions and images extracted from academic papers, patents, and technical reports (either one or multiple), and it interacts with engineers to iteratively refine the designs. After that, LADS configures and runs an optimizer to meet the design specifications. The effectiveness of LADS is demonstrated by a monopole slotted antenna generated from images and descriptions from the literature. To improve gain stability across the 3.1-10.6 GHz ultra-wide band, LADS modifies the cross-slot into an H-slot and changes substrate material, followed by parameter optimization. As a result, the gain variation is reduced while maintaining the same gain level. The LLM-enabled antenna modeling (LEAM) is available at: https://github.com/TaoWu974/LEAM.

cs.AI↗

arXiv2025

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Code and models are available at https://github.com/chenshunpeng/FoL

cs.CV↗

arXiv2025

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS. However, recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored. In this work, we propose ExCEL to explore CLIP's dense knowledge via a novel patch-text alignment paradigm for WSSS. Specifically, we propose Text Semantic Enrichment (TSE) and Visual Calibration (VC) modules to improve the dense alignment across both text and vision modalities. To make text embeddings semantically informative, our TSE module applies Large Language Models (LLMs) to build a dataset-wide knowledge base and enriches the text representations with an implicit attribute-hunting process. To mine fine-grained knowledge from visual features, our VC module first proposes Static Visual Calibration (SVC) to propagate fine-grained knowledge in a non-parametric manner. Then Learnable Visual Calibration (LVC) is further proposed to dynamically shift the frozen features towards distributions with diverse semantics. With these enhancements, ExCEL not only retains CLIP's training-free advantages but also significantly outperforms other state-of-the-art methods with much less training cost on PASCAL VOC and MS COCO.

cs.CV↗

arXiv2025

"Becoming My Own Audience": How Dancers React to Avatars Unlike Themselves in Motion Capture-Supported Live Improvisational Performance

The use of motion capture in live dance performances has created an emerging discipline enabling dancers to play different avatars on the digital stage. Unlike classical workflows, avatars enable performers to act as different characters in customized narratives, but research has yet to address how movement, improvisation, and perception change when dancers act as avatars. We created five avatars representing differing genders, shapes, and body limitations, and invited 15 dancers to improvise with each in practice and performance settings. Results show that dancers used avatars to distance themselves from their own habitual movements, exploring new ways of moving through differing physical constraints. Dancers explored using gender-stereotyped movements like powerful or feminine actions, experimenting with gender identity. However, focusing on avatars can coincide with a lack of continuity in improvisation. This work shows how emerging practices with performance technology enable dancers to improvise with new constraints, stepping outside the classical stage.

cs.HC↗

arXiv2025

RevTogether: Supporting Science Story Revision with Multiple AI Agents

As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents' decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling.

cs.HC↗

arXiv2024

MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the potential of LAM. Our findings suggest that imposing additional regularization on class-patch attention is necessary. To this end, we first view the attention as a novel directed graph and propose the Graph Category Representation module to implicitly regularize the interaction among class-patch entities. It ensures that class tokens dynamically condense the related patch information and suppress unrelated artifacts at a graph level. Second, motivated by the observation that CAM from classification weights maintains smooth localization of objects, we devise the Localization-informed Regularization module to explicitly regularize the class-patch attention. It directly mines the token relations from CAM and further supervises the consistency between class and patch tokens in a learnable manner. Extensive experiments are conducted on PASCAL VOC and MS COCO, validating that MoRe effectively addresses the artifact issue and achieves state-of-the-art performance, surpassing recent single-stage and even multi-stage methods. Code is available at https://github.com/zwyang6/MoRe.

cs.CV↗